© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73956
    Prev
    Next
    INDEX
    Explanations

    political entities and measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    abstract concepts and abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Benzyloxy
    0.51
    Contacto
    0.50
    Arg
    0.50
    SplashScreen
    0.50
    CONTACT
    0.49
    Contact
    0.48
    AnalyzeAction
    0.48
    󰡔
    0.47
    ClN
    0.46
    Contacts
    0.46
    POSITIVE LOGITS
     voters
    0.54
     Voters
    0.50
     veteran
    0.48
     Sulu
    0.47
     Republicans
    0.46
     electoral
    0.46
     Buddhist
    0.46
     shelling
    0.46
     Republican
    0.46
     incumbent
    0.46
    Activations Density 0.000%

    No Known Activations